1.安装环境
conda install pytorch=0.4.1 torchvision=0.2.1 -c pytorch
pip install tensorboardX==1.4
conda install opencv=3.3.1
模型
--model_name |
Training modality | Imagenet pretrained? | Model resolution | KITTI abs. rel. error | delta < 1.25 |
|---|---|---|---|---|---|
mono_640x192 |
Mono | Yes | 640 x 192 | 0.115 | 0.877 |
stereo_640x192 |
Stereo | Yes | 640 x 192 | 0.109 | 0.864 |
mono+stereo_640x192 |
Mono + Stereo | Yes | 640 x 192 | 0.106 | 0.874 |
mono_1024x320 |
Mono | Yes | 1024 x 320 | 0.115 | 0.879 |
stereo_1024x320 |
Stereo | Yes | 1024 x 320 | 0.107 | 0.874 |
mono+stereo_1024x320 |
Mono + Stereo | Yes | 1024 x 320 | 0.106 | 0.876 |
mono_no_pt_640x192 |
Mono | No | 640 x 192 | 0.132 | 0.845 |
stereo_no_pt_640x192 |
Stereo | No | 640 x 192 | 0.130 | 0.831 |
mono+stereo_no_pt_640x192 |
Mono + Stereo | No | 640 x 192 | 0.127 | 0.836 |
2.测试代码：
from __future__ import absolute_import, division, print_function
import os
import sys
import glob
import argparse
import numpy as np
import PIL.Image as pil
import matplotlib as mpl
import matplotlib.cm as cm
import torch
from torchvision import transforms, datasets
import networks
from layers import disp_to_depth
from utils import download_model_if_doesnt_exist
def parse_args():
parser = argparse.ArgumentParser(
description='Simple testing funtion for Monodepthv2 models.')
parser.add_argument('--image_path', type=str,
help='path to a test image or folder of images', required=True)
parser.add_argument('--model_name', type=str,
help='name of a pretrained model to use',
choices=[
"mono_640x192",
"stereo_640x192",
"mono+stereo_640x192",
"mono_no_pt_640x192",
"stereo_no_pt_640x192",
"mono+stereo_no_pt_640x192",
"mono_1024x320",
"stereo_1024x320",
"mono+stereo_1024x320"])
parser.add_argument('--ext', type=str,
help='image extension to search for in folder', default="jpg")
parser.add_argument("--no_cuda",
help='if set, disables CUDA',
action='store_true')
return parser.parse_args()
def test_simple(args):
"""Function to predict for a single image or folder of images
"""
assert args.model_name is not None, \
"You must specify the --model_name parameter; see README.md for an example"
if torch.cuda.is_available() and not args.no_cuda:
device = torch.device("cuda")
else:
device = torch.device("cpu")
download_model_if_doesnt_exist(args.model_name)
model_path = os.path.join("models", args.model_name)
print("-> Loading model from ", model_path)
encoder_path = os.path.join(model_path, "encoder.pth")
depth_decoder_path = os.path.join(model_path, "depth.pth")
# LOADING PRETRAINED MODEL
print(" Loading pretrained encoder")
encoder = networks.ResnetEncoder(18, False)
loaded_dict_enc = torch.load(encoder_path, map_location=device)
# extract the height and width of image that this model was trained with
feed_height = loaded_dict_enc['height']
feed_width = loaded_dict_enc['width']
filtered_dict_enc = {k: v for k, v in loaded_dict_enc.items() if k in encoder.state_dict()}
encoder.load_state_dict(filtered_dict_enc)
encoder.to(device)
encoder.eval()
print(" Loading pretrained decoder")
depth_decoder = networks.DepthDecoder(
num_ch_enc=encoder.num_ch_enc, scales=range(4))
loaded_dict = torch.load(depth_decoder_path, map_location=device)
depth_decoder.load_state_dict(loaded_dict)
depth_decoder.to(device)
depth_decoder.eval()
# FINDING INPUT IMAGES
if os.path.isfile(args.image_path):
# Only testing on a single image
paths = [args.image_path]
output_directory = os.path.dirname(args.image_path)
elif os.path.isdir(args.image_path):
# Searching folder for images
paths = glob.glob(os.path.join(args.image_path, '*.{}'.format(args.ext)))
output_directory = args.image_path
else:
raise Exception("Can not find args.image_path: {}".format(args.image_path))
print("-> Predicting on {:d} test images".format(len(paths)))
# PREDICTING ON EACH IMAGE IN TURN
with torch.no_grad():
for idx, image_path in enumerate(paths):
if image_path.endswith("_disp.jpg"):
# don't try to predict disparity for a disparity image!
continue
# Load image and preprocess
input_image = pil.open(image_path).convert('RGB')
original_width, original_height = input_image.size
input_image = input_image.resize((feed_width, feed_height), pil.LANCZOS)
input_image = transforms.ToTensor()(input_image).unsqueeze(0)
# PREDICTION
input_image = input_image.to(device)
features = encoder(input_image)
outputs = depth_decoder(features)
disp = outputs[("disp", 0)]
disp_resized = torch.nn.functional.interpolate(
disp, (original_height, original_width), mode="bilinear", align_corners=False)
# Saving numpy file
output_name = os.path.splitext(os.path.basename(image_path))[0]
name_dest_npy = os.path.join(output_directory, "{}_disp.npy".format(output_name))
scaled_disp, _ = disp_to_depth(disp, 0.1, 100)
np.save(name_dest_npy, scaled_disp.cpu().numpy())
# Saving colormapped depth image
disp_resized_np = disp_resized.squeeze().cpu().numpy()
vmax = np.percentile(disp_resized_np, 95)
normalizer = mpl.colors.Normalize(vmin=disp_resized_np.min(), vmax=vmax)
mapper = cm.ScalarMappable(norm=normalizer, cmap='magma')
colormapped_im = (mapper.to_rgba(disp_resized_np)[:, :, :3] * 255).astype(np.uint8)
im = pil.fromarray(colormapped_im)
name_dest_im = os.path.join(output_directory, "{}_disp.jpeg".format(output_name))
im.save(name_dest_im)
print(" Processed {:d} of {:d} images - saved prediction to {}".format(
idx + 1, len(paths), name_dest_im))
print('-> Done!')
if __name__ == '__main__':
args = parse_args()
test_simple(args)
3.测试图片：
4.测试效果
a.利用mono_640x192模型来预测
b.利用stereo_640x192模型来预测
c.利用mono+stereo_640x192模型来预测
剩下的模型就没测试了
总结：从效果图来看颜色的深浅反应了深度，颜色越深，表示深度大，表示距离远
来源：CSDN
作者：小土豆dy
链接：https://blog.csdn.net/qq_39431829/article/details/104159099